JP2000137813A - Individual identifier - Google Patents

Abstract

PROBLEM TO BE SOLVED: To decide an environmental change or biological change as a factor of rejection and to notify a user of the biological change if decided. SOLUTION: A history data base 6 stores a history of difference of degrees between an individual image and a dictionary 4, i.e., the result of collation between an individual to be identified and the dictionary 4. A biological change detection part 7 calculates the correlation between the history of degrees of difference and the base 6 based on the history of degrees of difference and decides a change of the biological feature of the individual if the said correlation is confirmed. The part 7 also calculates an approximate straight line of time series of the history of degrees of difference and decides a date as the notification timing for the second registration of the dictionary 4 when the degree of difference exceeds the prescribed value on the approximate straight line.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an individual identification apparatus for identifying individuals based on biological characteristics, and more particularly, to an individual identification device.
For example, the present invention relates to an animal individual identification device for registering data for individual identification of animals and performing collation in an organization requiring individual management of animals such as (race) horses and (pastoral) cows.

[0002]

2. Description of the Related Art Individual identification of thoroughbreds at a racetrack, auction field, or a breeding ranch is carried out under the initiative of a pedigree control agency. The current method of identifying individuals in Japan is based on coat color, vitiligo on the limbs, vitiligo on the head, and curl. In the world, there are other methods based on blood type, branding, tattooing, etc. Reference: "Knowledge of Horses", II-
3. How to identify a horse, P. 153-P. 154).

[0003] In the case of individual identification of cattle, a method using identification nameplates such as collars and ear tags and branding and tattooing has been adopted in general ranches.

[0004] As an individual identification method of an animal that has recently attracted attention, there is a technique using an MC (Micro Chip). This is a chip with a built-in microminiature integrated circuit enclosed in a glass tube, which is implanted in the body of an animal with an injector such as a syringe.In the case of identification, the embedded signal is traced by a non-contact detector to trace the output signal. This is used as information for individual identification.

[0005]

However, the above-mentioned prior art has the following problems to be solved.
In the case of discrimination based on coat color, white mark, vitiligo, and curl, there are many horses with few features and horses with the same feature, so that the identification of the horse is often incomplete. In addition, there is a risk that the branding and tattoos may disappear or be tampered with, and improvements in animal welfare such as pain and local suppuration received by animals have been desired. In addition, although individual identification based on blood type is accurate, there is a disadvantage that a considerable processing time is required for determination and the cost is high.

[0006] The identification nameplate has a risk of being damaged, lost or stolen, and in the case of branding or tattooing, it has a risk of disappearing or being tampered with like a horse. ing. In particular, even if this falsification is revealed, it is difficult to prove where the person originally belonged.

[0007] The MC method can be used semi-permanently once it is embedded, and also has advantages such as high convenience. However, the operability of implantation in living animals, pain given to animals at the time of implantation, local reactivity such as swelling, tenderness, suppuration, etc., motor dysfunction and clinical abnormalities in animals, movement of MC in vivo There are many issues in terms of performance, operability of detector, change in detection sensitivity, stability, and reliability. And above all, from the aspect of animal welfare, there are animal officials who are reluctant to adopt the MC method,
A convenient identification method that replaces the MC identification method has been desired.

[0008]

The present invention employs the following structure to solve the above-mentioned problems. <Structure 1> In an individual identification device that performs individual identification based on biological characteristics, a dictionary for individual identification provided in advance, and a difference between the individual and the dictionary, which is a result of collating the dictionary with the individual to be identified, are provided. A history database that stores the history and a correlation between the history of the dissimilarity and the time are calculated. If there is a correlation between the history of the dissimilarity and the time, the biological object that determines that the biological characteristic of the individual has changed is determined. An individual identification device comprising: a change detection unit.

<Structure 2> In the individual identification device according to claim 1, it is determined that there is a change in the biological characteristics of the individual.
An individual identification device comprising: a biometric change detection unit that sets a date and time when the difference on the approximate straight line of the time series of the difference history exceeds a predetermined value as a notification timing of dictionary re-registration.

<Structure 3> In the individual identification apparatus according to claim 1 or 2, the image database for storing all the image data of the collated result and the date of each image, and When it is determined that there is a change in the biological characteristics of the individual, from the image database, an image pair with the smallest degree of difference is obtained from an image group in which the shooting date of the individual is within a certain period, and shooting of the obtained image pair An individual identification device, comprising: a dictionary updating unit that updates a dictionary using a newer image as a registered dictionary.

<Structure 4> In an individual identification apparatus for performing individual identification based on biological characteristics, a dictionary for individual identification provided in advance and all image data as a result of collating the individual to be identified with the dictionary are stored. An image specifying unit that extracts a region having a large degree of difference between the image database to be stored and an image of the individual to be identified and the dictionary when the difference between the image and the dictionary is greater than a predetermined threshold value; An individual identification device, comprising: an area display unit that displays a specific area extracted in step (a) and an image of the individual in an image database.

[0012]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments of the present invention will be described below in detail with reference to specific examples. The invention relates to (race) horses,
(Maki) In order to identify animals at an organization that requires individual management of animals such as cattle, for example, register data on iris and iris granules and register data for collation processing.
The present invention relates to a verification device. Hereinafter, in each specific example, a case where a target animal is a horse in particular will be described as an example.

FIG. 2 is a front view of the eyeball of the horse. As shown in FIG. 2, the horse's eye mainly includes a pupil 10, an iris (iris) 11, and an iris granule 12 between upper and lower eyelids 13.

A transparent hemispherically raised cornea is provided in front of the pupil 10 and the iris 11. The major difference between horse eyes and human eyes is that the pupil 10 is elliptical,
It is to have iris granules 12 unique to horses and ruminants.

Light from the outside passes through the pupil 10 and reaches the retina at the back of the pupil. The iris 11 is a muscle surrounding the pupil 10 and has a function of controlling the amount of light incident on the pupil 10 by contracting and expanding. The iris granules 12 are located between the iris 11 and the pupil 10 and have a shape in which hemispherical raised granules are connected. The iris granules 12 have a black color rich in melanin pigment, and are said to have a function of absorbing dazzling daylight even when the iris 11 contracts.

The size and shape of the iris 11 and the iris granules 12 or the fine wrinkles and irregularities on the surface differ depending on the individual of the horse and the right and left eyes, and there are individual differences. for that reason,
The iris 11 and the iris granules 12 are registered as reference data (hereinafter, referred to as a "dictionary") by imaging the horse's eyes with a camera, and the iris 11 and the iris granule data obtained at the time of the examination are compared and compared with the dictionary. It is possible to identify the target individual.

However, since the iris and iris granules are one organ of the living body, the shape, pattern, color, and other characteristics may differ from those at the time of registration due to disease or damage.

In such a case, even if the dictionary is compared with the dictionary by the above method, there are many differences from the dictionary, and it is not possible to identify the horse as a correct horse, so the dictionary must be re-registered.

In general, the re-registration work needs to restrain the horse and the manager of the horse for a certain period of time, so it is desirable to reduce the frequency as much as possible. However, as a method of knowing a change due to a disease or the like, in camera collation with the dictionary, there is no other than empirically detecting an increase in reject frequency due to an identification error. It is also difficult to identify the cause of rejection by distinguishing between the change in the living body of the horse and the environmental change, because it also occurs due to environmental changes such as mydriasis and miosis due to changes in the shooting size or changes in gaze movement and illuminance. .

Therefore, there is a possibility that delay in re-registration or unnecessary re-registration work may occur, which may impose a burden on the management work of the supervising organization of the individual.

According to the present invention, on the other hand, in the individual identification device, the collation history is left, and the cause of a plurality of continuous rejects is distinguished from the environmental change and the biological change from the collation history, and notified to the user. With the function, the re-registration timing is made suitable.
Hereinafter, the individual identification device of the present invention will be described in detail using specific examples.

<< Specific Example 1 >> In Specific Example 1, it is checked whether the difference between the input image and the dictionary is correlated with time, and if there is a correlation, it is determined that there is a biological change, and The user is notified according to the change level.

<Structure> FIG. 1 is a diagram showing the structure of a specific example 1 of the individual identification apparatus of the present invention. Specific example 1 includes an ID input unit 1, an imaging unit 2, a collation unit 3, a dictionary 4, a history recording unit 5, a history database (DB) 6, a biological change detection unit 7, and a display unit 8.
Consists of

The ID input unit 1 is an interface with a user for inputting an ID number given to a horse to be identified at the time of registration, and is a keyboard, a pen-type input device, or the like. The ID input unit 1 has a dictionary selection / read function, and has a function of reading a dictionary of an input ID. It should be noted that different numbers are assigned to the IDs on the right and left sides of the horse's eyes.

The image pickup section 2 comprises an image input section such as a CCD video camera and an illumination device for certifying an individual.
It captures the image of the horse's eyes as a signal. The image input unit is a part that captures an image of a horse's eye with a camera, and performs a process of converting analog optical information of the image of the horse's eye into a digital electric signal by a sensor. Also, the lighting device is provided to illuminate the horse's eyes in order to capture it with good contrast,
As a light source, light having a wavelength that is hardly perceived by an animal, such as red light, near-infrared light, or infrared light, is used to prevent the horse from dazzling and moving excessively.

The collating unit 3 selects the dictionary data of the horse with the ID number from the dictionary 4, reads it into a memory (not shown), compares it with the horse data obtained by the imaging unit 2, and calculates the difference (hereinafter, this function is referred to as the horse data). The difference is called a dissimilarity), and a true / false judgment function for judging whether or not the horse is the same as the dictionary based on whether the dissimilarity is within a threshold value.

The dictionary 4 is an image database of registered horses created at the time of registration, and includes a registered horse ID and its image data.

The history recording unit 5 has a built-in timer, checks the date of collation from the timer, and records it in the history database 6 together with the degree of difference calculated by the collation unit 3.

The history database 6 is a storage section of the collation history, and includes a list of collation dates and differences provided for each horse ID.

The biological change detecting unit 7 detects the cause of rejection,
This is a functional unit that distinguishes between environmental change and biological change, and includes a history data reading function, a time correlation calculation function, and a change level calculation function. That is, the biological change detecting unit 7 calculates the correlation between the history of the degree of difference and the time, and when there is a correlation between the history of the degree of difference and the time, determines that the biological characteristic of the individual has changed. When the difference on the approximate straight line of the time series of the difference history exceeds a predetermined value, the date and time are set as the notification timing of dictionary re-registration.

The display unit 8 has a function of displaying the authenticity determination result / dissimilarity received from the output result of the collation unit 3 and a notification function of re-registration received from the output result of the biometric change detection unit 7. Output device.

In the above specific example, the collating unit 3, the history recording unit 5, and the biological change detecting unit 7 are realized by a processor executing a program corresponding to each function. Further, such a program is provided by being recorded on a recording medium.

<Operation> FIG. 3 is a flowchart showing the operation of the first embodiment of the present invention. The steps will be described below in order.

[Step S1] The ID input unit 1 receives an input of an ID number from a user.

[Step S2] The ID input unit 1
The ID number received from the user is sent to the dictionary 4. Dictionary 4 is
The image data of the corresponding number is retrieved from the list based on the ID number and returned.

[Step S3] The processing of the next step 3 is performed by the imaging section 2. The horse's eyes are illuminated by an illuminator using red, near-infrared, or infrared light as a light source, and imaged by an image input device such as a CCD video camera. The CCD sensor is configured by a two-dimensional array of photoelectric conversion elements, and exposes reflected light of an imaging target for a certain period of time, and quantizes a voltage level imprinted by the photoelectric conversion at a certain gradation to convert it into a digital signal. Thus, a two-dimensional array of image frames is obtained.

[Step S4] Step S4 and the following steps S5 and S6 are performed by the collating unit 3. The matching unit 3 compares the dictionary with the image of the identification target horse obtained from the imaging unit 2 and calculates the degree of difference d. As a method of calculating the degree of difference, a known technique such as an average difference between each pixel of the image of the horse to be identified and the dictionary image and a Euclidean distance can be applied to this specific example.

[Step S5] The collation unit 3 performs a true / false determination based on the degree of difference. As a method for determining the authenticity, the degree of difference is compared with a predetermined threshold, and if the degree of difference is equal to or less than the threshold, the inspection target is determined to be true; if not, the method is determined to be false. Discrimination technology is applicable.

If the result of the true / false determination is "true", the flow proceeds to the history recording processing in step S7, and if the result is "false", the flow proceeds to the rejection processing in step S6.

[Step S6] The collating unit 3 displays on the display unit 8 that the identification result is rejected,
The process proceeds to subsequent re-identification processing. This display processing is performed by the display unit.

[Step S7] Step S7 is performed by the history recording unit 5 and the history database 6. The history recording unit 5 sends the horse ID and the degree of difference to the history database 6 only when it is determined to be true in the truth determination in step S5. The history database 6 has a built-in timer, finds the date at the time of recording by the timer, and additionally records it in the column of the ID list of the corresponding horse along with the degree of difference.

[Step S8] Steps S8 to S10
Is performed by the biological change detecting unit 7. The biometric change detection unit 7 reads the history data of the ID of the horse to be tested from the history database 6. Since the data is a two-dimensional data series of the date and the difference, the correlation coefficient R of the date and the difference is
Is possible. The correlation coefficient R is the date ti
And the difference is di (i is the data number and the number of data N), and the average is μt and μd, respectively. FIG. 4 is an explanatory diagram of an arithmetic expression of the correlation coefficient R.

[Step S9] As in step S8, 2
A first approximation straight line is obtained using the history data of the dimensional series, and the degree of difference (hereinafter, referred to as a change level) at the time of inspection on the first approximation straight line is calculated. This is performed in order to know the change level at the time of inspection and determine the timing of user notification.

[Step S10] A change with time is detected using the correlation coefficient R and the change level. That is, when the correlation coefficient R and the change level are both equal to or greater than a predetermined value, it is determined that there is a change with time, and the process proceeds to the warning process in step S12.
If not, the process proceeds to the accepting process of step S11.

FIG. 5 is an explanatory diagram of the biological change detecting method. 5A shows an example in which there is no change with time, and FIG.
Is a plot of the relationship between the identification date and the degree of difference in an example having a change with time.

As shown in FIG. 5A, even when there is no change with time, the degree of difference varies due to a change in the photographing environment, but is usually uncorrelated with the collation date and time. On the other hand, when there is a change with time as shown in FIG. 5B, the change tends to increase with a certain positive correlation. Therefore, a change with time can be detected based on whether the correlation coefficient R is equal to or more than a certain value. Further, since the frequency of occurrence of rejection can be determined based on the change level at the time of examination, a notification timing can be determined by setting a threshold value for notifying a biological change. That is, in the case of FIG. 5B, the primary approximation line indicated by the broken line is extended, and the date and time of the point at which this line exceeds the biological change notification threshold (the point where the linear approximation line and the line of the biological change notification threshold intersect) are notified. Day.

[Step S11] The display unit 8 displays that the identification result is "accept" and ends the processing.

[Step S12] A biological change is detected.
The fact that re-registration is necessary is displayed on the display unit 8 to notify the user, and the process proceeds to the accepting process in step S11.

<Effects> As described above, according to this example, the following effects can be expected. ● By providing the history recording unit 5, the history database 6, and the biological change detecting unit 7 in the animal individual identification device,
The device automatically detects the degradation of the identification accuracy, determines whether the degradation is due to a biological change, and if the degradation is due to a biological change, sends a signal prompting the user to re-register the dictionary. In addition, the user can re-register the dictionary at a suitable timing, which is expected to have an effect of reducing convenience and unnecessary re-registration due to deterioration of identification accuracy.

<< Specific Example 2 >> The individual identification apparatus described in Specific Example 1 is a method of detecting a biological change of an iris and an iris granule based on a collation history and notifying a user of a time for re-registering a dictionary. Re-registration of the dictionary can be very laborious if the number of heads is large. Therefore, a specific example 2 describes an individual identification device having an automatic dictionary registration function.

<Structure> FIG. 6 is a diagram showing the structure of a specific example 2 of the individual identification apparatus according to the present invention. As shown in FIG. 6, this specific example includes an ID input unit 101, an imaging unit 102, a collation unit 10
3. Dictionary 104, history recording unit 105, history database (DB) 106, image recording unit 107, image database (DB) 108, biological change detecting unit 109, dictionary updating unit 1
10, the display unit 111.

This embodiment is characterized in that an image recording unit 107, an image database 108, and a dictionary updating unit 110 are provided in addition to the history recording unit 105, the history database 106, and the biological change detecting unit 109, which are the same as those of the first embodiment. Thus, a function of reconstructing a dictionary to an optimum one at the time of detecting a biological change is added based on the stored image every time the matching is performed.

The ID input unit 101 to the history database 106 and the biological change detecting unit 109 in the second embodiment are the same as the ID input unit 1 to the history database 6 and the biological change detecting unit 7 in the first embodiment. Description is omitted.

The image recording unit 107 is a functional unit that has a built-in timer, checks the date of collation from the timer, and records it in the image database 108 together with the image obtained by the imaging unit 102.

The image database 108 is a storage unit for the collation images, and includes a collation date and a list of image data provided for each horse ID.

The dictionary updating unit 110 is provided with the biological change detecting unit 10.
9 is activated only when it is determined that the dictionary needs to be updated, the dictionary selection function from the image database 108 and the dictionary 1
04 re-registration function. That is, the dictionary updating unit 110
When a detection result of a biometric change is received from the biometric change detection unit 109, an image pair having a minimum degree of difference is obtained from an image group in which a shooting date is within a certain period from the image database 106,
In addition, the dictionary 104 has a function of updating the dictionary 104 with a new image on the shooting date of the obtained image pair as a registered dictionary.

The display unit 111 has a function of displaying the truth / false judgment result / dissimilarity having received the output result of the collation unit 103 and a function of notifying the dictionary update result having received the output result of the dictionary updating unit 110. Output device.

Incidentally, in the above specific example, the collating unit 103,
The history recording unit 105, the image recording unit 107, the biological change detecting unit 109, and the dictionary updating unit 110 are realized by a processor executing a program corresponding to each function. Further, such a program is provided by being recorded on a recording medium.

<Operation> FIG. 7 is a flowchart for explaining the operation of the second embodiment.

[Step S101] The ID input unit 101 receives a horse ID number input by the user.

[Step S102] ID input section 101
Sends the ID number received from the user to the dictionary 104. The dictionary 104 retrieves the image data of the corresponding number from the list based on the ID number and returns it.

[Step S103] Step S103
Is performed by the imaging unit 102. The horse's eyes are illuminated by an illuminator using red, near-infrared, or infrared light as a light source, and imaged by an image input device such as a CCD video camera. The CCD sensor is configured by a two-dimensionally arranged photoelectric conversion element, and exposes the reflected light of the imaging target for a certain period of time, and converts the voltage level imprinted by the photoelectric conversion into a digital signal by quantizing it at a certain gradation. Thus, a two-dimensional array of image frames is obtained.

[Step S104] Steps S104 to S104
S106 is performed by the matching unit 103. Collation unit 1
In step 03, the degree of difference d is calculated by comparing the dictionary with the image of the identification target horse obtained from the imaging unit 102. As in the first embodiment, a known technique such as an average difference between each pixel of the image of the horse to be identified and the dictionary image and a Euclidean distance can be applied as a method of calculating the difference.

[Step S105] The collation unit 103 determines the authenticity based on the degree of difference. Various methods can be applied as the authenticity determination method.For example, the degree of difference is compared with a predetermined threshold, and if the degree of difference is equal to or less than the threshold, the inspection target is assumed to be true. Is false. If the result of the authenticity determination is “true”, the flow proceeds to the history recording process of step S107, and if the result is “false”, the flow proceeds to the rejection process of step S106.

[Step S106] The collation section 103 displays on the display section 111 that the identification result is rejected, and proceeds to the re-identification processing after step S103. This display process is performed by the display unit 111.

[Step S107] The processing in step S107 is performed by the history recording unit 105 and the history database 10
6. The history recording unit 105 sends the horse ID and the degree of difference to the history database 106 only when the result of the determination in step S105 is true. The history database 106 has a built-in timer, finds the date at the time of recording by the timer, and additionally records it in the column of the ID list of the corresponding horse along with the degree of difference.

[Step S108] The processing in step S108 is performed by the image recording unit 107 and the image database 108.
Done by The image recording unit 107 includes the history recording unit 1
Date information is obtained from 05 and the date and the image are registered in the image database 108. The image database 108 is a horse
A list of dates and images is provided for each D, and the list is added to already recorded data.

[Step S109] Steps S109 to S109
S111 is performed by the biological change detecting unit 109. The biological change detection unit 109 reads the history data of the ID of the horse to be tested from the history database 106. Since the data is a two-dimensional data series of the date and the degree of difference, specific example 1
Similarly, the correlation coefficient R between the date and the degree of difference is obtained.

[Step S110] Biological change detecting section 10
In step 9, as in the first embodiment, a first approximation straight line is obtained using two-dimensional series history data, and the degree of difference (change level) at the time of inspection on the first approximation straight line is calculated.

[Step S111] A temporal change is detected using the correlation coefficient R and the change level. That is, when both the correlation coefficient R and the change level are equal to or greater than a predetermined value, it is determined that there is a temporal change, and the process proceeds to the dictionary update process from step S113. Otherwise, the process proceeds to an accept process (step S112).

[Step S112] The fact that the identification result is accept is displayed on the display unit 111, and the processing is terminated.

[Step S113] Steps S113 to S113
The process of S115 is performed by the dictionary update unit 110.
The dictionary update unit 110 receives the result of the change detection from the biological change detection unit 109, and reads out the image of the ID of the horse to be tested and the collation date from the image database 108.

[Step S114] One image to be updated is selected and determined from the images read out in step S113. In the image selection method, an image group whose shooting date is within a certain period is first selected from the read images, the difference between any pairs of the image groups is calculated, and the pair having the minimum difference is obtained. Then, the image having the newer shooting date is selected as a registered dictionary. As a result, it is possible to select a new dictionary that is stable with the least influence of environmental changes and that has a new shooting date.

[Step S115] Dictionary update unit 110
Updates the dictionary by overwriting the selected dictionary in the corresponding ID column of the dictionary 104. Then, step S1
Proceeding to the accept process of No. 12, the display unit 111 displays that the dictionary has been updated.

<Effects> As described above, according to the specific example 2, the following effects can be expected. In the animal individual identification device, the history recording unit 105, the history database 106, the image recording unit 107, the image database 108, the biological change detecting unit 109, and the dictionary updating unit 11
By providing 0, the apparatus automatically detects the deterioration of the identification accuracy, determines whether the deterioration is due to a biological change, and further, if the accuracy is deteriorated due to a biological change, the photographing date and time In addition, since the dictionary is updated with a low influence of environmental change, it is possible to stably maintain low erroneous identification following changes in the living body. As a result, the effect of reducing the convenience and the trouble of re-registration due to frequent rejects due to the deterioration of the identification accuracy can be expected.

<< Specific Example 3 >> The individual identification apparatus described in the specific examples 1 and 2 detects a biological change of the iris and the iris granule based on the collation history and notifies the user or automatically updates the dictionary. This was a specific example. On the other hand, in the specific example 3, when the biological change is suspected based on the collation result, the region is identified and displayed to identify the biological change, thereby assisting the user in finding the biological change.

<Structure> FIG. 8 is a diagram showing the structure of a specific example 3 of the individual identification apparatus according to the present invention. As shown in FIG. 8, this specific example includes an ID input unit 201, an imaging unit 202, a collation unit 203,
It comprises a dictionary 204, an image recording unit 205, an area specifying unit 206, an image database 207, and a display unit 208. Furthermore,
The display unit 208 includes an area display unit 209 and an identification result display unit 210.

The feature of this specific example is that, by providing the area specifying unit 206, the image database 207, and the area display unit 209, the biometric change area is specified, and a past collation image is displayed to the user.

The ID input unit 201, the imaging unit 202, the collation unit 203, the dictionary 204, and the image recording unit 205 are the same as the ID input unit 101, the imaging unit 102, and the collation unit 1 in the second embodiment.
03, the configuration of the dictionary 104 and the image recording unit 107, and a description thereof will be omitted.

The area specifying unit 206 has a function of determining the level of difference, an image history reading function, and an area specifying function. That is, the area specifying unit 206 determines the degree of difference between the image of the identification target individual and the dictionary 204 by using a predetermined threshold (th
2) If it is larger, it has a function of extracting an area having a large degree of difference in these images.

The image database 207 is a storage section for collation images, and includes a collation date and a list of image data provided for each horse ID.

As described above, the display unit 208 includes the region display unit 209 and the identification result display unit 210, has a function of displaying the output results of the region identification unit 206 and the collation unit 203, respectively, and has an output device such as a display or a printer. Consisting of The area display unit 209 includes the area specifying unit 206
Is a display unit that displays the specific area extracted in step (1) and the image of the corresponding ID read from the image database 207. The identification result display unit 210 is a display unit for displaying whether or not the identification result is an accept.

In the above specific example, the collating unit 203,
The image recording unit 205 and the area specifying unit 206 are realized by executing a program corresponding to each function by a processor. Further, such a program is provided by being recorded on a recording medium.

<Operation> FIG. 9 is a flowchart showing the operation of the third embodiment. Hereinafter, each step will be described in order.

[Step S201] ID input section 201
Receives the horse ID number entered by the user.

[Step S202] ID input section 201
Sends the ID number received from the user to the dictionary 204. The dictionary 204 retrieves the image data of the corresponding number from the list based on the ID number and returns it.

[Step S203] The process of step S203 is performed by the imaging section 202. The horse's eyes are illuminated by an illuminator using red, near-infrared, or infrared light as a light source, and imaged by an image input device such as a CCD video camera. The CCD sensor is configured by a two-dimensionally arranged photoelectric conversion element, and exposes the reflected light of the imaging target for a certain period of time, and converts the voltage level imprinted by the photoelectric conversion into a digital signal by quantizing it at a certain gradation. Thus, a two-dimensional array of image frames is obtained.

[Step S204] Steps S204 to S204
The process of S206 is performed by the matching unit 203. The matching unit 203 compares the dictionary with the image of the identification target horse obtained from the imaging unit 202, and calculates the degree of difference d. As the method of calculating the degree of difference, as in the first and second embodiments, a known technique such as an average difference between each pixel of the image of the horse to be identified and the dictionary image and a Euclidean distance can be applied.

[Step S205] The collation unit 203 performs a true / false determination based on the degree of difference. The authenticity discrimination method is a method in which the degree of difference is compared with a predetermined threshold value, and when the degree of difference is equal to or less than the threshold value, the test object is determined to be true, and when not, the test object is determined to be false. It is not done. If the result of the authenticity determination is “true”, step S20
The process proceeds to the image recording process of No. 7, and when it is determined to be “false”, the process proceeds to the reject process of step S206.

[Step S206] The collation unit 203 displays on the display unit 208 that the identification result is rejected, and proceeds to the re-identification processing after step S203. This display process is performed by the display unit 208.

[Step S207] The processing in step S207 is performed by the image recording unit 205 and the image database 20.
7 is performed. The image recording unit 205 sends the horse ID and the image to the image database 207 only when the authenticity is determined to be true in Step S205. The image database 207 additionally records an image in the column of the horse ID list of the corresponding horse.

[Step S208] The processing in steps S208 and S209 is performed by the area specifying section 206. The area specifying unit 206 first performs step S204
Is compared with the threshold value th2. Threshold th2
Is smaller than the threshold th used in step S205,
In other words, the threshold value is a strict value, which is used to find an input image that is determined to be true and that has relatively many differences from the dictionary. Therefore, if the value is smaller than the threshold, the process directly proceeds to the accepting process of step S212,
If the difference is larger than the threshold value, the process proceeds to the next step S209, in which the area having a large degree of difference is specified.

[Step S209] When the differences between the pixels of the dictionary image and the input image are compared, the pixels whose differences are larger than a predetermined required value are obtained, and the X and Y coordinate values of these pixels are determined. (Xmin, Ymi
n) and the maximum values (Xmax, Ymax). Thereby, four points (Xmin, Ymin), (Xmin, Ymax), (Xmax,
Since a circumscribed rectangle formed by connecting (Ymax) and (Xmax, Ymin) is extracted, the inside of the circumscribed rectangle can be defined as a region having a large degree of difference.

[Step S210] Steps S210 to S210
The process of S212 is performed by the display unit 208. The area display unit 209 reads, from the image database 207, an image having the same ID that has been collated in the past to display the image to the user.

[Step S211] Area display section 209
Displays the past image and the input image read in step S210 on a display device such as a display. At this time, the rectangle obtained in step S109 is displayed and shown on each of the past images in order to make the display easy for the user to understand.

FIG. 10 is an explanatory diagram of a display example of the changing section. As shown in the figure, the feature of this specific example is to display the image history of an area having a large degree of difference to the user, thereby assisting visual confirmation of biological changes.

[Step S212] Finally, the display unit 20
The identification result display unit 210 of FIG. 8 displays on the display unit 208 that the identification result is “accept”, and ends the processing.

<Effects> As described above, according to the third embodiment, the following effects can be expected. -In the animal individual identification device, by providing the image recording unit 205, the image database 207, the region specifying unit 206, and the region display unit 209, a region suspected of a biological change is specified, and a past image is provided to the user. Because it can be displayed, every time verification is performed, the living body can be easily checked visually.
It is possible to expect an effect that a lesion or damage of a living body can be found at an early stage, and a countermeasure such as re-registration of a dictionary can be performed at a suitable timing.

<< Usage Form >> Each of the above specific examples has been described as a device for identifying an iris and an iris granule, but can be generally used for a device for identifying any living body that changes.

In the above embodiments, the matching has been described using an image. However, the principle of the present invention can be applied to the case where various features extracted from the image are used.

In the first and second embodiments, the difference degree history is linearly approximated in order to obtain the change level at the time of collation. However, a higher-order or non-linear approximation function capable of better approximation can be applied. is there.

The case where a horse is used as an individual to be identified has been described. However, the present invention is not limited to this, and other animals or humans can be similarly applied.

[Brief description of the drawings]

FIG. 1 is a configuration diagram showing a specific example 1 of an individual identification device of the present invention.

FIG. 2 is an explanatory diagram of an eyeball image of a horse.

FIG. 3 is a flowchart showing an operation of a specific example 1 of the individual identification device of the present invention.

FIG. 4 is an explanatory diagram of an arithmetic expression of a correlation coefficient R in the specific example 1 of the individual identification device of the present invention.

FIG. 5 is an explanatory diagram of a biological change detection method in a specific example 1 of the individual identification device of the present invention.

FIG. 6 is a configuration diagram showing a specific example 2 of the individual identification device of the present invention.

FIG. 7 is a flowchart showing an operation of a specific example 2 of the individual identification apparatus of the present invention.

FIG. 8 is a configuration diagram of a specific example 3 of the individual identification device of the present invention.

FIG. 9 is a flowchart showing the operation of the specific example 3 of the individual identification device of the present invention.

FIG. 10 is an explanatory diagram of a display example of a changing unit in a specific example 3 of the individual identification device of the present invention.

[Explanation of symbols]

 4, 104, 204 Dictionary 6, 106 History database 7 Biological change detection unit 108, 207 Image database 110 Dictionary update unit 206 Area identification unit 209 Area display unit

Claims (4)

[Claims] 1. An individual identification device for performing individual identification based on a biological characteristic, comprising: a dictionary provided for individual identification provided in advance; and an individual and a dictionary, which are a result of collating the individual to be identified with the dictionary. A history database that stores the history of the degree of difference, and calculates the correlation between the history of the degree of difference and time, and when there is a correlation between the history of the degree of difference and time, the change in the biological characteristics of the individual is An individual identification device, comprising: a biological change detection unit that determines that there is a change. 2. The individual identification device according to claim 1, wherein it is determined that there is a change in the biological characteristic of the individual, and the degree of difference on the approximate straight line of the time series of the degree of difference exceeds a predetermined value. In this case, the individual identification device includes a biological change detecting unit that uses the date and time as the notification timing of dictionary re-registration. 3. The individual identification device according to claim 1, wherein an image database storing all image data as a result of the collation and data of the date of each image, If it is determined that there has been a change in the biological characteristics, from the image database, the image date of the individual is determined from a group of images within a certain period, and an image pair having the minimum degree of difference is determined. A dictionary updating unit that updates the dictionary with a newer image as a registered dictionary. 4. An individual identification apparatus for performing individual identification based on biological characteristics, wherein a dictionary for individual identification provided in advance and all image data as a result of collating the individual to be identified with the dictionary are stored. An image database; an area specifying unit that extracts an area having a high degree of difference in the images when the degree of difference between the image of the individual to be identified and the dictionary is greater than a predetermined threshold value; An individual identification device comprising: a specific region extracted by the unit; and an area display unit that displays an image of the individual in the image database.